{ "schemaVersion": 1, "project": "test-witness", "projectVersion": "0.1.0", "mode": "authored-fixtures", "startedAt": "2026-10-11T05:47:42.540Z", "completedAt": "2026-10-11T05:47:44.220Z", "runtime": { "node": "v22.23.3", "java": "openjdk version \"21.0.12.1\" 2026-08-18 LTS\nOpenJDK Runtime Environment Temurin-21.0.12.1+1 (build 21.0.12.1+1-LTS)\nOpenJDK 64-Bit Server VM Temurin-21.0.12.1+1 (build 21.0.12.1+1-LTS, mixed mode, sharing)", "javac": "javac 21.0.12.1" }, "sourceRevision": "6a375f0b5f0c0c26c9563613e5aa0cbb808c94b9", "logsPathNormalized": true, "inputSha256": { "demos/CONTRACT.md": "06a8f401aba0d714ac76be35658b0ee038e8124364abe2e7b1c952eb39e775c9", "demos/lib.mjs": "ce111bc9472b48b5d149a3a79392f8acf150d82206491eeb0e12c97ed3412754", "demos/test-witness/README.md": "5fabc13ec73362cad69f22e4b9791305f64bd26947b4e6a93b6abc02b3ff1175", "demos/test-witness/fixtures/Witness.java": "10621a725271d7be6acfc6765191ae654fcfb98589d1a5886acd8c7ed3342bad", "demos/test-witness/run.mjs": "c7dfef54b46176c81f17a9f4d617cd749232c21bb81482c46a111ad66cc5e503" }, "scope": "Five authored invoice assertions and three seeded defects; acceptance of test evidence only.", "limitations": [ "No generated tests or held-out performance evaluation.", "No measured time savings or customer ROI.", "Trusted local Java fixtures; temporary execution is not a security sandbox.", "Hashes establish consistency, not malicious-tamper authenticity." ], "observations": [ { "id": "correct-strong", "caseId": "correct", "role": "baseline", "expected": "All five assertions pass", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" }, { "id": "rounding", "status": "PASS", "actual": "1.01", "expected": "1.01" }, { "id": "below-threshold", "status": "PASS", "actual": "99.00", "expected": "99.00" }, { "id": "threshold", "status": "PASS", "actual": "90.00", "expected": "90.00" }, { "id": "validation", "status": "PASS", "actual": "rejected", "expected": "rejected" } ], "exitCode": 0 }, "verdict": "accepted", "reason": "Correct implementation must pass every declared assertion", "commandIds": [ "command-3", "command-4" ] }, { "id": "rounding-weak", "caseId": "rounding", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 1, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" } ], "exitCode": 0 }, "verdict": "rejected", "reason": "Weak suite passes while omitting the assertion for the seeded defect", "commandIds": [ "command-3", "command-5" ] }, { "id": "rounding-strong", "caseId": "rounding", "role": "candidate", "expected": "Only rounding assertion fails", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" }, { "id": "rounding", "status": "FAIL", "actual": "1.00", "expected": "1.01" }, { "id": "below-threshold", "status": "PASS", "actual": "99.00", "expected": "99.00" }, { "id": "threshold", "status": "PASS", "actual": "90.00", "expected": "90.00" }, { "id": "validation", "status": "PASS", "actual": "rejected", "expected": "rejected" } ], "exitCode": 1 }, "verdict": "accepted", "reason": "Detection requires precisely the assertion ID assigned to the seeded defect", "commandIds": [ "command-3", "command-6" ] }, { "id": "threshold-weak", "caseId": "threshold", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 1, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" } ], "exitCode": 0 }, "verdict": "rejected", "reason": "Weak suite passes while omitting the assertion for the seeded defect", "commandIds": [ "command-3", "command-7" ] }, { "id": "threshold-strong", "caseId": "threshold", "role": "candidate", "expected": "Only threshold assertion fails", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" }, { "id": "rounding", "status": "PASS", "actual": "1.01", "expected": "1.01" }, { "id": "below-threshold", "status": "PASS", "actual": "99.00", "expected": "99.00" }, { "id": "threshold", "status": "FAIL", "actual": "100.00", "expected": "90.00" }, { "id": "validation", "status": "PASS", "actual": "rejected", "expected": "rejected" } ], "exitCode": 1 }, "verdict": "accepted", "reason": "Detection requires precisely the assertion ID assigned to the seeded defect", "commandIds": [ "command-3", "command-8" ] }, { "id": "validation-weak", "caseId": "validation", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 1, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" } ], "exitCode": 0 }, "verdict": "rejected", "reason": "Weak suite passes while omitting the assertion for the seeded defect", "commandIds": [ "command-3", "command-9" ] }, { "id": "validation-strong", "caseId": "validation", "role": "candidate", "expected": "Only validation assertion fails", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" }, { "id": "rounding", "status": "PASS", "actual": "1.01", "expected": "1.01" }, { "id": "below-threshold", "status": "PASS", "actual": "99.00", "expected": "99.00" }, { "id": "threshold", "status": "PASS", "actual": "90.00", "expected": "90.00" }, { "id": "validation", "status": "FAIL", "actual": "allowed", "expected": "rejected" } ], "exitCode": 1 }, "verdict": "accepted", "reason": "Detection requires precisely the assertion ID assigned to the seeded defect", "commandIds": [ "command-3", "command-10" ] }, { "id": "correct-always-pass", "caseId": "correct", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" }, { "id": "rounding", "status": "PASS", "actual": "1.01", "expected": "1.01" }, { "id": "below-threshold", "status": "PASS", "actual": "99.00", "expected": "99.00" }, { "id": "threshold", "status": "PASS", "actual": "90.00", "expected": "90.00" }, { "id": "validation", "status": "PASS", "actual": "rejected", "expected": "rejected" } ], "exitCode": 0 }, "verdict": "rejected", "reason": "Unconditional suites cannot qualify: they ignore implementation behavior", "commandIds": [ "command-3", "command-11" ] }, { "id": "rounding-always-pass", "caseId": "rounding", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "PASS", "actual": "4.00", "expected": "4.00" }, { "id": "rounding", "status": "PASS", "actual": "1.01", "expected": "1.01" }, { "id": "below-threshold", "status": "PASS", "actual": "99.00", "expected": "99.00" }, { "id": "threshold", "status": "PASS", "actual": "90.00", "expected": "90.00" }, { "id": "validation", "status": "PASS", "actual": "rejected", "expected": "rejected" } ], "exitCode": 0 }, "verdict": "rejected", "reason": "Unconditional suites cannot qualify: they ignore implementation behavior", "commandIds": [ "command-3", "command-12" ] }, { "id": "correct-always-fail", "caseId": "correct", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 5, "assertions": [ { "id": "ordinary", "status": "FAIL", "actual": "unconditional-failure", "expected": "4.00" }, { "id": "rounding", "status": "FAIL", "actual": "unconditional-failure", "expected": "1.01" }, { "id": "below-threshold", "status": "FAIL", "actual": "unconditional-failure", "expected": "99.00" }, { "id": "threshold", "status": "FAIL", "actual": "unconditional-failure", "expected": "90.00" }, { "id": "validation", "status": "FAIL", "actual": "unconditional-failure", "expected": "rejected" } ], "exitCode": 1 }, "verdict": "rejected", "reason": "Unconditional suites cannot qualify: they ignore implementation behavior", "commandIds": [ "command-3", "command-13" ] }, { "id": "correct-missing", "caseId": "correct", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 0, "assertions": [], "exitCode": 0 }, "verdict": "inconclusive", "reason": "Execution or assertion evidence missing; never a detected defect", "commandIds": [ "command-3", "command-14" ] }, { "id": "correct-crash", "caseId": "correct", "role": "negative-control", "expected": "Cannot qualify as an adequate test suite", "actual": { "assertionCount": 0, "assertions": [], "exitCode": 1 }, "verdict": "inconclusive", "reason": "Execution or assertion evidence missing; never a detected defect", "commandIds": [ "command-3", "command-15" ] } ], "commands": [ { "id": "command-1", "executable": "java", "args": [ "-version" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "", "stderr": "openjdk version \"21.0.12.1\" 2026-08-18 LTS\nOpenJDK Runtime Environment Temurin-21.0.12.1+1 (build 21.0.12.1+1-LTS)\nOpenJDK 64-Bit Server VM Temurin-21.0.12.1+1 (build 21.0.12.1+1-LTS, mixed mode, sharing)\n", "durationMs": 130 }, { "id": "command-2", "executable": "javac", "args": [ "-version" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "javac 21.0.12.1\n", "stderr": "", "durationMs": 347 }, { "id": "command-3", "executable": "javac", "args": [ "-d", "", "demos/test-witness/fixtures/Witness.java" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "", "stderr": "", "durationMs": 644 }, { "id": "command-4", "executable": "java", "args": [ "-cp", "", "Witness", "correct", "strong" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nASSERT|rounding|PASS|1.01|1.01\nASSERT|below-threshold|PASS|99.00|99.00\nASSERT|threshold|PASS|90.00|90.00\nASSERT|validation|PASS|rejected|rejected\nSUMMARY|0\n", "stderr": "", "durationMs": 49 }, { "id": "command-5", "executable": "java", "args": [ "-cp", "", "Witness", "rounding", "weak" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nSUMMARY|0\n", "stderr": "", "durationMs": 47 }, { "id": "command-6", "executable": "java", "args": [ "-cp", "", "Witness", "rounding", "strong" ], "cwd": "", "status": "completed", "exitCode": 1, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nASSERT|rounding|FAIL|1.00|1.01\nASSERT|below-threshold|PASS|99.00|99.00\nASSERT|threshold|PASS|90.00|90.00\nASSERT|validation|PASS|rejected|rejected\nSUMMARY|1\n", "stderr": "", "durationMs": 52 }, { "id": "command-7", "executable": "java", "args": [ "-cp", "", "Witness", "threshold", "weak" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nSUMMARY|0\n", "stderr": "", "durationMs": 45 }, { "id": "command-8", "executable": "java", "args": [ "-cp", "", "Witness", "threshold", "strong" ], "cwd": "", "status": "completed", "exitCode": 1, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nASSERT|rounding|PASS|1.01|1.01\nASSERT|below-threshold|PASS|99.00|99.00\nASSERT|threshold|FAIL|100.00|90.00\nASSERT|validation|PASS|rejected|rejected\nSUMMARY|1\n", "stderr": "", "durationMs": 53 }, { "id": "command-9", "executable": "java", "args": [ "-cp", "", "Witness", "validation", "weak" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nSUMMARY|0\n", "stderr": "", "durationMs": 46 }, { "id": "command-10", "executable": "java", "args": [ "-cp", "", "Witness", "validation", "strong" ], "cwd": "", "status": "completed", "exitCode": 1, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nASSERT|rounding|PASS|1.01|1.01\nASSERT|below-threshold|PASS|99.00|99.00\nASSERT|threshold|PASS|90.00|90.00\nASSERT|validation|FAIL|allowed|rejected\nSUMMARY|1\n", "stderr": "", "durationMs": 63 }, { "id": "command-11", "executable": "java", "args": [ "-cp", "", "Witness", "correct", "always-pass" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nASSERT|rounding|PASS|1.01|1.01\nASSERT|below-threshold|PASS|99.00|99.00\nASSERT|threshold|PASS|90.00|90.00\nASSERT|validation|PASS|rejected|rejected\nSUMMARY|0\n", "stderr": "", "durationMs": 47 }, { "id": "command-12", "executable": "java", "args": [ "-cp", "", "Witness", "rounding", "always-pass" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "ASSERT|ordinary|PASS|4.00|4.00\nASSERT|rounding|PASS|1.01|1.01\nASSERT|below-threshold|PASS|99.00|99.00\nASSERT|threshold|PASS|90.00|90.00\nASSERT|validation|PASS|rejected|rejected\nSUMMARY|0\n", "stderr": "", "durationMs": 46 }, { "id": "command-13", "executable": "java", "args": [ "-cp", "", "Witness", "correct", "always-fail" ], "cwd": "", "status": "completed", "exitCode": 1, "stdout": "ASSERT|ordinary|FAIL|unconditional-failure|4.00\nASSERT|rounding|FAIL|unconditional-failure|1.01\nASSERT|below-threshold|FAIL|unconditional-failure|99.00\nASSERT|threshold|FAIL|unconditional-failure|90.00\nASSERT|validation|FAIL|unconditional-failure|rejected\nSUMMARY|5\n", "stderr": "", "durationMs": 52 }, { "id": "command-14", "executable": "java", "args": [ "-cp", "", "Witness", "correct", "missing" ], "cwd": "", "status": "completed", "exitCode": 0, "stdout": "No assertions executed\n", "stderr": "", "durationMs": 27 }, { "id": "command-15", "executable": "java", "args": [ "-cp", "", "Witness", "correct", "crash" ], "cwd": "", "status": "completed", "exitCode": 1, "stdout": "", "stderr": "Exception in thread \"main\" java.lang.RuntimeException: unknown execution failure\n\tat Witness.main(Witness.java:14)\n", "durationMs": 26 } ], "metrics": [ { "id": "defects-detected", "numerator": 3, "denominator": 3, "unit": "eligible seeded defects", "definition": "Strong-suite assertion failures uniquely attributed to rounding, threshold or validation seeds; unresolved excluded." }, { "id": "unresolved", "numerator": 2, "denominator": 12, "unit": "executions", "definition": "Missing-assertion and unknown crash controls retained as inconclusive, never detections." } ], "experimentVerdict": "passed", "workingTree": { "dirty": true, "description": "Uncommitted working tree; base revision does not identify these edits. Input hashes identify executed sources." }, "runId": "29bb03f4-8bc4-4d79-9e8e-fc92a604d1f2", "environment": "GitHub Actions", "workflowRun": "https://github.com/odin-labs-ai/odin-rnd/actions/runs/38115932001", "workflowAttempt": 1 }